hermes-agent/locales/en.yaml
Teknium c39168453d
feat(i18n): localize all gateway commands + web dashboard, add 8 new locales (16 total) (#22914)
* feat(i18n): localize /model command output

Reported by @tianma8888: when Chinese users run /model, the labels
("Provider:", "Context:", "_session only_", etc.) are still English.
This routes the static prose through the existing i18n catalog so it
follows display.language / HERMES_LANGUAGE.

Changes:
- locales/{en,zh,ja,de,es,fr,tr,uk}.yaml: add 17 keys under
  gateway.model.* covering switched/provider/context/max_output/cost/
  capabilities/prompt_caching/warning/saved_global/session_only_hint/
  current_label/current_tag/more_models_suffix/usage_*.
- gateway/run.py _handle_model_command: replace hardcoded f-strings in
  the picker callback, the text-list fallback, and the direct-switch
  confirmation block with t("gateway.model.<key>", ...).

What stays English:
- model IDs, provider slugs, capability strings, cost figures, and the
  "[Note: model was just switched...]" prepended to the model's next
  prompt (LLM-facing, not user-facing).
- The two slightly-different session-only hints unify on a single key
  with the em-dash phrasing.

Validation: tests/agent/test_i18n.py 27/27 passing (parity contract
holds), tests/gateway/ -k 'model or i18n' 74/74 passing.

* feat(i18n): localize all gateway slash command outputs

Expands the i18n catalog from 7 strings to 234 keys across 35 gateway
slash command handlers, so non-English users see localized output for
\`/profile\`, \`/status\`, \`/help\`, \`/personality\`, \`/voice\`, \`/reset\`,
\`/agents\`, \`/restart\`, \`/commands\`, \`/goal\`, \`/retry\`, \`/undo\`,
\`/sethome\`, \`/title\`, \`/yolo\`, \`/background\`, \`/approve\`, \`/deny\`,
\`/insights\`, \`/debug\`, \`/rollback\`, \`/reasoning\`, \`/fast\`,
\`/verbose\`, \`/footer\`, \`/compress\`, \`/topic\`, \`/kanban\`,
\`/resume\`, \`/branch\`, \`/usage\`, \`/reload-mcp\`, \`/reload-skills\`,
\`/update\`, \`/stop\` (plus the \`/model\` block already added in the
previous commit).

Reported by @tianma8888 — Chinese users want command output prose in
their language, not just the labels we already had.

Translations are hand-written for all 8 supported locales (en, zh, ja,
de, es, fr, tr, uk), matching each catalog's existing style: full-width
punctuation in zh, em-dashes in zh/ja/uk, French spaced colons,
German noun capitalization, etc.

What stays English (unchanged):
- Identifiers/values: model IDs, file paths, profile names, session IDs,
  command flag names like --global, URLs, config keys.
- Backtick code spans: \`/foo\`, \`config.yaml\`.
- Log messages (logger.info/warning/error).
- LLM-facing system notes prepended to next prompt (e.g. [Note: model
  was just switched...]).
- Strings produced by external modules (gateway_help_lines,
  format_gateway, manual_compression_feedback) — those have their
  own surfaces.

New shared keys for cross-handler boilerplate:
- gateway.shared.session_db_unavailable (5 call sites: branch, title,
  resume, topic, _disable_telegram_topic_mode_for_chat)
- gateway.shared.session_not_found (1 site)
- gateway.shared.warn_passthrough (2 sites in /title's f"⚠️ {e}" pattern)

YAML gotcha fixed: \`yolo.on\` and \`yolo.off\` were originally written
unquoted, which YAML 1.1 parses as boolean True/False keys. Renamed to
\`yolo.enabled\` / \`yolo.disabled\` for both safety and clarity.

Test fix: tests/agent/test_i18n.py::test_t_missing_key_in_non_english_falls_back_to_english
now resets the catalog cache on teardown, so the fake "foo: English Foo"
locale doesn't poison the module-level cache for subsequent tests in
the same xdist worker. (Without this, every gateway slash command test
that shares a worker with the i18n suite would see the fake catalog.)

Validation:
- tests/agent/test_i18n.py: 27/27 (parity contract — every key in every
  locale, matching placeholder tokens).
- tests/gateway/: 5077 passed, 0 failed (full gateway suite).
- 180 t() call sites added across 35 handlers; 1872 catalog entries
  total (234 keys × 8 locales).

* feat(i18n): add 8 new locales — af, ko, it, ga, zh-hant, pt, ru, hu

Expands the static-message catalog from 8 → 16 languages, each with full
270-key parity against the English source-of-truth.  Every locale now
covers the same surface PR #22914 added: approval prompts plus all 35
gateway slash command outputs.

New locales:
- af  Afrikaans      (community ask in #21961 by @GodsBoy; PRs #21962, #21970)
- ko  Korean         (PRs #20297 by @tmdgusya, #22285 by @project820)
- it  Italian        (PR #20371 by @leprincep35700)
- ga  Irish/Gaeilge  (PR #20962 by @ryanmcc09-dot)
- zh-hant Traditional Chinese (PRs #20523 by @jackey8616, #13140 by @anomixer)
- pt  Portuguese     (PRs #20443 by @pedroborges, #15737 by @carloshenriquecarniatto, #22063 by @Magaav)
- ru  Russian        (PR #22770 by @DrMaks22)
- hu  Hungarian      (PR #22336 by @lunasec007)

Each locale uses native-quality translations matching the existing tone
and conventions of the older 8 locales:
- zh-hant uses 繁體 characters with TW/HK technical vocabulary (軟體
  not 软件, 連線 not 连接, 設定 not 设置, 訊息 not 消息, 工作階段 not 会话, 程式
  not 程序, 預設 not 默认, 伺服器 not 服务器), full-width punctuation 「:()」.
- ko uses formal 합니다체 (습니다/합니다) register throughout.
- pt uses European Portuguese as baseline with neutral PT/BR vocabulary
  where possible.
- ga uses standard An Caighdeán Oifigiúil; English loanwords retained
  for tech terms without good Irish equivalents (gateway, API, JSON).
- All preserve {placeholder} tokens, backtick code spans, slash commands,
  brand names (Hermes, MCP, TTS, YOLO, OpenAI, Telegram, etc.), and emoji.

Aliases added in agent/i18n.py:
- af-za, Afrikaans → af
- ko-kr, Korean, 한국어 → ko
- it-it, italiano → it
- ga-ie, Irish, Gaeilge → ga
- zh-tw, zh-hk, zh-mo, traditional-chinese → zh-hant (note: zh-tw used to
  alias to zh; now aliases to its own zh-hant catalog)
- zh-cn, zh-hans, zh-sg → zh (unchanged from before)
- pt-pt, pt-br, brazilian, portuguese → pt
- ru-ru, Russian, русский → ru
- hu-hu, Magyar → hu

The zh-tw alias re-routing is intentional: previously typing 'zh-TW' got
the Simplified Chinese catalog (wrong vocabulary for Taiwan/HK users).
Now those users get the proper Traditional Chinese catalog.

Validation:
- tests/agent/test_i18n.py: 43/43 (parity contract holds for all 16
  languages × 270 keys = 4320 catalog entries, with matching placeholder
  tokens).
- E2E alias resolution verified for all 19 alias inputs (Afrikaans, ko-KR,
  한국어, italiano, Gaeilge, zh-TW, zh-HK, traditional-chinese, pt-BR,
  brazilian, Magyar, etc.).
- tests/gateway/: 5198 passed (3 pre-existing TTS routing failures
  unrelated to i18n).

Credit to all contributors whose PRs surfaced these language requests.
Their original PRs may now be closed as superseded with credit.

* feat(dashboard-i18n): add 14 web dashboard locales matching the static catalog

Brings the React dashboard (web/src/) up to the same 16-language
coverage the static catalog already has after the previous commits in
this PR. The Translations interface is TypeScript-typed, so every new
locale must provide every key — tsc -b is the parity guard.

Languages added (each is a complete 429-line locale file):
- af  Afrikaans
- ja  Japanese        (PR #22513 by @snuffxxx surfaced this)
- de  German          (PR #21749 by @mag1art)
- es  Spanish         (PR #21749)
- fr  French          (PRs #21749, #10310 by @foXaCe)
- tr  Turkish
- uk  Ukrainian
- ko  Korean          (PRs #21749, #18894 by @ovstng, #22285 by @project820)
- it  Italian
- ga  Irish (Gaeilge)
- zh-hant Traditional Chinese (PR #13140 by @anomixer)
- pt  Portuguese      (PRs #22063 by @Magaav, #22182 by @wesleysimplicio, #15737 by @carloshenriquecarniatto)
- ru  Russian         (PRs #21749, #22770 by @DrMaks22)
- hu  Hungarian       (PR #22336 by @lunasec007)

Each translation covers all 15 namespaces with full key parity vs en.ts,
preserves every {placeholder} token verbatim, keeps identifiers
untranslated (brand names, file paths, cron expressions, code spans),
translates the language.switchTo tooltip into the target language, and
matches existing tone conventions (zh-hant uses TW/HK vocab; ja uses
formal desu/masu; ko uses formal seumnida register; ga uses An
Caighdean Oifigiuil with English loanwords for tech vocab without good
Irish equivalents).

Plumbing:
- web/src/i18n/types.ts: Locale union expanded to all 16 codes.
- web/src/i18n/context.tsx: imports all 16 catalogs; exports
  LOCALE_META (endonym + flag per locale); isLocale() type guard.
- web/src/i18n/index.ts: re-export LOCALE_META.
- web/src/components/LanguageSwitcher.tsx: replaced two-state EN-ZH
  toggle with a click-to-open dropdown listing all 16 languages.

Note: zh-hant.ts exports zhHant (camelCase) since hyphen is invalid in
a JS identifier; the canonical 'zh-hant' string keys it in TRANSLATIONS.

Validation:
- npx tsc -b: 0 errors. Every locale satisfies Translations.
- npm run build (tsc + vite production): green, 2062 modules.
- Each locale file is exactly 429 lines.

Out of scope: plugin dashboards (kanban/achievements ship as prebuilt
bundles with no source in repo); Docusaurus docs (separate surface);
TUI (no i18n yet).

* feat(plugin-i18n): localize achievements + kanban plugin dashboards across all 16 locales

Brings the two shipped plugin dashboards (hermes-achievements, kanban)
under the same i18n umbrella as the core dashboard PR #22914 just
established.  Both bundles now read user-facing strings from the host's
i18n catalog via SDK.useI18n() instead of hardcoded English.

## Approach

Plugin dashboards ship as prebuilt IIFE bundles in
plugins/<name>/dashboard/dist/index.js — no build step, no source in
repo (upstream-authored, vendored as compiled JS).  Earlier contributor
PRs (#22594, #22595, #18747) tried direct edits but didn't actually
wire the bundles to read translations.

This change does the wiring properly:

1.  Each bundle gets a useI18n shim at IIFE scope:
        const useI18n = SDK.useI18n
          || function () { return { t: { kanban: null }, locale: "en" }; };
    Older host SDKs without useI18n still load the bundle and render
    English fallbacks.

2.  A small tx(t, path, fallback, vars) helper resolves dotted keys
    under the plugin's namespace (t.kanban.* or t.achievements.*) and
    interpolates {placeholder} tokens.

3.  Every React component starts with const { t } = useI18n() and
    each user-visible string is wrapped in tx(t, "key", "English fallback").
    Helpers called outside React components (window.prompt callers,
    constants used during init) take t as a parameter.

4.  Top-level constants that were English dictionaries (COLUMN_LABEL,
    COLUMN_HELP, DESTRUCTIVE_TRANSITIONS, DIAGNOSTIC_EVENT_LABELS in
    kanban) become getColumnLabel(t, status)-style functions backed by
    FALLBACK_* dictionaries.

## Translations added

Two new top-level namespaces added to the dashboard's TypeScript-typed
Translations interface:

- achievements: ~70 keys covering the hero, scan banner, achievement
  card, share dialog, stats, filters, and empty states.
- kanban: ~145 keys covering the board, columns (with nested
  columnLabels and columnHelp sub-dicts), card detail panel,
  bulk-actions toolbar, dependency editor, board switcher, and
  diagnostic callouts.

Each key is provided across all 16 supported locales:
en, zh, zh-hant, ja, de, es, fr, tr, uk, af, ko, it, ga, pt, ru, hu.

Total new translation entries: ~3,440 (215 keys × 16 locales).

## What stays English (deliberate)

- API paths, CSS class names, data-* attributes, JSON keys, regex
  strings, URLs, file paths (~/.hermes/kanban.db, boards/_archived/).
- State identifier strings used as lookup keys (triage / todo / ready /
  running / blocked / done / archived) — labels translate, key strings
  don't.
- The PNG share-card text rendered to canvas in the achievements
  ShareDialog (HERMES AGENT watermark, UNLOCKED stamp, tier names) —
  these become part of a globally-shared image and stay English.
- localStorage keys (hermes.kanban.selectedBoard).
- Brand names (Kanban, Hermes, WebSocket, Nous Research).

## Contributor credit

PR #22594 by @02356abc and PR #22595 by @02356abc supplied the
en + zh kanban namespace skeleton (145 keys); used as the en source-
of-truth in this commit and translated to the other 14 locales.

PR #18747 by @laolaoshiren first surfaced the achievements
localization request.

## Validation

- npx tsc -b: 0 errors. All 16 locale .ts files satisfy the
  Translations type with full key parity.
- npm run build (tsc + vite production build): green, 2062 modules,
  1.56MB JS / 95KB CSS, ~2.5s build.
- node --check on both plugin bundles: parse cleanly.
- 126 tx() call sites in kanban, 46 in achievements.

## Out of scope

- TUI (ui-tui/) has no i18n infrastructure yet.
- Docusaurus docs (website/i18n/) — already had zh-Hans; expanding
  is a separate translation workstream (Thai / Korean / Hindi PRs).
2026-05-10 07:14:14 -07:00

365 lines
23 KiB
YAML
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Hermes static-message catalog -- English (baseline / source of truth)
#
# Only user-facing static messages from the CLI approval prompt and a handful
# of gateway slash-command replies live here. Agent-generated output, log
# lines, error tracebacks, tool outputs, and slash-command descriptions stay
# in English and are NOT translated -- see agent/i18n.py for scope rationale.
#
# Keys are dotted paths; nesting below is purely for readability. Values may
# contain {placeholder} tokens for str.format substitution. When adding a
# new key, add it to EVERY locale file (en/zh/ja/de/es/fr/tr/uk) in the same commit --
# tests/agent/test_i18n.py asserts catalog parity.
approval:
# CLI approval prompt -- shown when a dangerous command needs user review.
dangerous_header: "⚠️ DANGEROUS COMMAND: {description}"
choose_long: " [o]nce | [s]ession | [a]lways | [d]eny"
choose_short: " [o]nce | [s]ession | [d]eny"
prompt_long: " Choice [o/s/a/D]: "
prompt_short: " Choice [o/s/D]: "
timeout: " ⏱ Timeout - denying command"
allowed_once: " ✓ Allowed once"
allowed_session: " ✓ Allowed for this session"
allowed_always: " ✓ Added to permanent allowlist"
denied: " ✗ Denied"
cancelled: " ✗ Cancelled"
blocklist_message: "This command is on the unconditional blocklist and cannot be approved."
gateway:
# Messenger replies to slash commands and implicit state changes.
approval_expired: "⚠️ Approval expired (agent is no longer waiting). Ask the agent to try again."
draining: "⏳ Draining {count} active agent(s) before restart..."
goal_cleared: "✓ Goal cleared."
no_active_goal: "No active goal."
config_read_failed: "⚠️ Could not read config.yaml: {error}"
config_save_failed: "⚠️ Could not save config: {error}"
# /model command output -- shown after a model switch or when listing models.
# Provider names, model IDs, capability strings, and cost figures are NOT
# translated -- they're identifiers/values, not prose. Only the labels
# ("Provider:", "Context:", etc.) and the help/footer lines are localized.
model:
error_prefix: "Error: {error}"
switched: "Model switched to `{model}`"
provider_label: "Provider: {provider}"
context_label: "Context: {tokens} tokens"
max_output_label: "Max output: {tokens} tokens"
cost_label: "Cost: {cost}"
capabilities_label: "Capabilities: {capabilities}"
prompt_caching_enabled: "Prompt caching: enabled"
warning_prefix: "Warning: {warning}"
saved_global: "Saved to config.yaml (`--global`)"
session_only_hint: "_(session only — add `--global` to persist)_"
current_label: "Current: `{model}` on {provider}"
current_tag: " (current)"
more_models_suffix: " (+{count} more)"
usage_switch_model: "`/model <name>` — switch model"
usage_switch_provider: "`/model <name> --provider <slug>` — switch provider"
usage_persist: "`/model <name> --global` — persist"
agents:
header: "🤖 **Active Agents & Tasks**"
active_agents: "**Active agents:** {count}"
this_chat: " · this chat"
more: "... and {count} more"
running_processes: "**Running background processes:** {count}"
async_jobs: "**Gateway async jobs:** {count}"
none: "No active agents or running tasks."
state_starting: "starting"
state_running: "running"
approve:
no_pending: "No pending command to approve."
once_singular: "✅ Command approved. The agent is resuming..."
once_plural: "✅ Commands approved ({count} commands). The agent is resuming..."
session_singular: "✅ Command approved (pattern approved for this session). The agent is resuming..."
session_plural: "✅ Commands approved (pattern approved for this session) ({count} commands). The agent is resuming..."
always_singular: "✅ Command approved (pattern approved permanently). The agent is resuming..."
always_plural: "✅ Commands approved (pattern approved permanently) ({count} commands). The agent is resuming..."
background:
usage: "Usage: /background <prompt>\nExample: /background Summarize the top HN stories today\n\nRuns the prompt in a separate session. You can keep chatting — the result will appear here when done."
started: "🔄 Background task started: \"{preview}\"\nTask ID: {task_id}\nYou can keep chatting — results will appear when done."
branch:
db_unavailable: "Session database not available."
no_conversation: "No conversation to branch — send a message first."
create_failed: "Failed to create branch: {error}"
switch_failed: "Branch created but failed to switch to it."
branched_one: "⑂ Branched to **{title}** ({count} message copied)\nOriginal: `{parent}`\nBranch: `{new}`\nUse `/resume` to switch back to the original."
branched_many: "⑂ Branched to **{title}** ({count} messages copied)\nOriginal: `{parent}`\nBranch: `{new}`\nUse `/resume` to switch back to the original."
commands:
usage: "Usage: `/commands [page]`"
skill_header: "⚡ **Skill Commands**:"
default_desc: "Skill command"
none: "No commands available."
header: "📚 **Commands** ({total} total, page {page}/{total_pages})"
nav_prev: "`/commands {page}` ← prev"
nav_next: "next → `/commands {page}`"
out_of_range: "_(Requested page {requested} was out of range, showing page {page}.)_"
compress:
not_enough: "Not enough conversation to compress (need at least 4 messages)."
no_provider: "No provider configured -- cannot compress."
nothing_to_do: "Nothing to compress yet (the transcript is still all protected context)."
focus_line: "Focus: \"{topic}\""
summary_failed: "⚠️ Summary generation failed ({error}). {count} historical message(s) were removed and replaced with a placeholder; earlier context is no longer recoverable. Consider checking your auxiliary.compression model configuration."
aux_failed: " Configured compression model `{model}` failed ({error}). Recovered using your main model — context is intact — but you may want to check `auxiliary.compression.model` in config.yaml."
failed: "Compression failed: {error}"
debug:
upload_failed: "✗ Failed to upload debug report: {error}"
header: "**Debug report uploaded:**"
auto_delete: "⏱ Pastes will auto-delete in 6 hours."
full_logs_hint: "For full log uploads, use `hermes debug share` from the CLI."
share_hint: "Share these links with the Hermes team for support."
deny:
stale: "❌ Command denied (approval was stale)."
no_pending: "No pending command to deny."
denied_singular: "❌ Command denied."
denied_plural: "❌ Commands denied ({count} commands)."
fast:
not_supported: "⚡ /fast is only available for OpenAI models that support Priority Processing."
status: "⚡ Priority Processing\n\nCurrent mode: `{mode}`\n\n_Usage:_ `/fast <normal|fast|status>`"
unknown_arg: "⚠️ Unknown argument: `{arg}`\n\n**Valid options:** normal, fast, status"
saved: "⚡ ✓ Priority Processing: **{label}** (saved to config)\n_(takes effect on next message)_"
session_only: "⚡ ✓ Priority Processing: **{label}** (this session only)"
label_fast: "FAST"
label_normal: "NORMAL"
status_fast: "fast"
status_normal: "normal"
footer:
status: "📎 Runtime footer: **{state}**\nFields: `{fields}`\nPlatform: `{platform}`"
usage: "Usage: `/footer [on|off|status]`"
saved: "📎 Runtime footer: **{state}**{example}\n_(saved globally — takes effect on next message)_"
example_line: "\nExample: `{preview}`"
state_on: "ON"
state_off: "OFF"
goal:
unavailable: "Goals unavailable on this session."
no_goal_set: "No goal set."
paused: "⏸ Goal paused: {goal}"
no_resume: "No goal to resume."
resumed: "▶ Goal resumed: {goal}\nSend any message to continue, or wait — I'll take the next step on the next turn."
invalid: "Invalid goal: {error}"
set: "⊙ Goal set ({budget}-turn budget): {goal}\nI'll keep working until the goal is done, you pause/clear it, or the budget is exhausted.\nControls: /goal status · /goal pause · /goal resume · /goal clear"
help:
header: "📖 **Hermes Commands**\n"
skill_header: "\n⚡ **Skill Commands** ({count} active):"
more_use_commands: "\n... and {count} more. Use `/commands` for the full paginated list."
insights:
invalid_days: "Invalid --days value: {value}"
error: "Error generating insights: {error}"
kanban:
error_prefix: "⚠ kanban error: {error}"
subscribed_suffix: "(subscribed — you'll be notified when {task_id} completes or blocks)"
truncated_suffix: "… (truncated; use `hermes kanban …` in your terminal for full output)"
no_output: "(no output)"
personality:
none_configured: "No personalities configured in `{path}/config.yaml`"
header: "🎭 **Available Personalities**\n"
none_option: "• `none` — (no personality overlay)"
item: "• `{name}` — {preview}"
usage: "\nUsage: `/personality <name>`"
save_failed: "⚠️ Failed to save personality change: {error}"
cleared: "🎭 Personality cleared — using base agent behavior.\n_(takes effect on next message)_"
set_to: "🎭 Personality set to **{name}**\n_(takes effect on next message)_"
unknown: "Unknown personality: `{name}`\n\nAvailable: {available}"
profile:
header: "👤 **Profile:** `{profile}`"
home: "📂 **Home:** `{home}`"
reasoning:
level_default: "medium (default)"
level_disabled: "none (disabled)"
scope_session: "session override"
scope_global: "global config"
status: "🧠 **Reasoning Settings**\n\n**Effort:** `{level}`\n**Scope:** {scope}\n**Display:** {display}\n\n_Usage:_ `/reasoning <none|minimal|low|medium|high|xhigh|reset|show|hide> [--global]`"
display_on: "on ✓"
display_off: "off"
display_set_on: "🧠 ✓ Reasoning display: **ON**\nModel thinking will be shown before each response on **{platform}**."
display_set_off: "🧠 ✓ Reasoning display: **OFF** for **{platform}**"
reset_global_unsupported: "⚠️ `/reasoning reset --global` is not supported. Use `/reasoning <level> --global` to change the global default."
reset_done: "🧠 ✓ Session reasoning override cleared; falling back to global config."
unknown_arg: "⚠️ Unknown argument: `{arg}`\n\n**Valid levels:** none, minimal, low, medium, high, xhigh\n**Display:** show, hide\n**Persist:** add `--global` to save beyond this session"
set_global: "🧠 ✓ Reasoning effort set to `{effort}` (saved to config)\n_(takes effect on next message)_"
set_global_save_failed: "🧠 ✓ Reasoning effort set to `{effort}` (session only — config save failed)\n_(takes effect on next message)_"
set_session: "🧠 ✓ Reasoning effort set to `{effort}` (session only — add `--global` to persist)\n_(takes effect on next message)_"
reload_mcp:
cancelled: "🟡 /reload-mcp cancelled. MCP tools unchanged."
always_followup: " Future `/reload-mcp` calls will run without confirmation. Re-enable via `approvals.mcp_reload_confirm: true` in config.yaml."
confirm_prompt: "⚠️ **Confirm /reload-mcp**\n\nReloading MCP servers rebuilds the tool set for this session and **invalidates the provider prompt cache** — the next message will re-send full input tokens. On long-context or high-reasoning models this can be expensive.\n\nChoose:\n• **Approve Once** — reload now\n• **Always Approve** — reload now and silence this prompt permanently\n• **Cancel** — leave MCP tools unchanged\n\n_Text fallback: reply `/approve`, `/always`, or `/cancel`._"
header: "🔄 **MCP Servers Reloaded**\n"
reconnected: "♻️ Reconnected: {names}"
added: " Added: {names}"
removed: " Removed: {names}"
none_connected: "No MCP servers connected."
tools_available: "\n🔧 {tools} tool(s) available from {servers} server(s)"
failed: "❌ MCP reload failed: {error}"
reload_skills:
header: "🔄 **Skills Reloaded**\n"
no_new: "No new skills detected."
total: "\n📚 {count} skill(s) available"
added_header: " **Added Skills:**"
removed_header: " **Removed Skills:**"
item_with_desc: " - {name}: {desc}"
item_no_desc: " - {name}"
failed: "❌ Skills reload failed: {error}"
reset:
header_default: "✨ Session reset! Starting fresh."
header_new: "✨ New session started!"
header_titled: "✨ New session started: {title}"
title_rejected: "\n⚠ Title rejected: {error}"
title_error_untitled: "\n⚠ {error} — session started untitled."
title_empty_untitled: "\n⚠ Title is empty after cleanup — session started untitled."
tip: "\n✦ Tip: {tip}"
restart:
in_progress: "⏳ Gateway restart already in progress..."
restarting: "♻ Restarting gateway. If you aren't notified within 60 seconds, restart from the console with `hermes gateway restart`."
resume:
db_unavailable: "Session database not available."
no_named_sessions: "No named sessions found.\nUse `/title My Session` to name your current session, then `/resume My Session` to return to it later."
list_header: "📋 **Named Sessions**\n"
list_item: "• **{title}**{preview_part}"
list_preview_suffix: " — _{preview}_"
list_footer: "\nUsage: `/resume <session name>`"
list_failed: "Could not list sessions: {error}"
not_found: "No session found matching '**{name}**'.\nUse `/resume` with no arguments to see available sessions."
already_on: "📌 Already on session **{name}**."
switch_failed: "Failed to switch session."
resumed_one: "↻ Resumed session **{title}** ({count} message). Conversation restored."
resumed_many: "↻ Resumed session **{title}** ({count} messages). Conversation restored."
resumed_no_count: "↻ Resumed session **{title}**. Conversation restored."
retry:
no_previous: "No previous message to retry."
rollback:
not_enabled: "Checkpoints are not enabled.\nEnable in config.yaml:\n```\ncheckpoints:\n enabled: true\n```"
none_found: "No checkpoints found for {cwd}"
invalid_number: "Invalid checkpoint number. Use 1-{max}."
restored: "✅ Restored to checkpoint {hash}: {reason}\nA pre-rollback snapshot was saved automatically."
restore_failed: "❌ {error}"
set_home:
save_failed: "Failed to save home channel: {error}"
success: "✅ Home channel set to **{name}** (ID: {chat_id}).\nCron jobs and cross-platform messages will be delivered here."
status:
header: "📊 **Hermes Gateway Status**"
session_id: "**Session ID:** `{session_id}`"
title: "**Title:** {title}"
created: "**Created:** {timestamp}"
last_activity: "**Last Activity:** {timestamp}"
tokens: "**Tokens:** {tokens}"
agent_running: "**Agent Running:** {state}"
state_yes: "Yes ⚡"
state_no: "No"
queued: "**Queued follow-ups:** {count}"
platforms: "**Connected Platforms:** {platforms}"
stop:
stopped_pending: "⚡ Stopped. The agent hadn't started yet — you can continue this session."
stopped: "⚡ Stopped. You can continue this session."
no_active: "No active task to stop."
title:
db_unavailable: "Session database not available."
warn_prefix: "⚠️ {error}"
empty_after_clean: "⚠️ Title is empty after cleanup. Please use printable characters."
set_to: "✏️ Session title set: **{title}**"
not_found: "Session not found in database."
current_with_title: "📌 Session: `{session_id}`\nTitle: **{title}**"
current_no_title: "📌 Session: `{session_id}`\nNo title set. Usage: `/title My Session Name`"
topic:
not_telegram_dm: "The /topic command is only available in Telegram private chats."
no_session_db: "Session database not available."
unauthorized: "You are not authorized to use /topic on this bot."
restore_needs_topic: "To restore a session, first create or open a Telegram topic, then send /topic <session-id> inside that topic. To create a new topic, open All Messages and send any message there."
topics_disabled: "Telegram topics are not enabled for this bot yet.\n\nHow to enable them:\n1. Open @BotFather.\n2. Choose your bot.\n3. Open Bot Settings → Threads Settings.\n4. Turn on Threaded Mode and make sure users are allowed to create new threads.\n\nThen send /topic again."
topics_user_disallowed: "Telegram topics are enabled, but users are not allowed to create topics.\n\nOpen @BotFather → choose your bot → Bot Settings → Threads Settings, then turn off 'Disallow users to create new threads'.\n\nThen send /topic again."
enable_failed: "Failed to enable Telegram topic mode: {error}"
bound_status: "This topic is linked to:\nSession: {label}\nID: {session_id}\n\nUse /new to replace this topic with a fresh session.\nFor parallel work, open All Messages and send a message there to create another topic."
thread_ready: "Telegram multi-session topics are enabled.\n\nThis topic will be used as an independent Hermes session. Use /new to replace this topic's current session. For parallel work, open All Messages and send a message there to create another topic."
untitled_session: "Untitled session"
undo:
nothing: "Nothing to undo."
removed: "↩️ Undid {count} message(s).\nRemoved: \"{preview}\""
update:
platform_not_messaging: "✗ /update is only available from messaging platforms. Run `hermes update` from the terminal."
not_git_repo: "✗ Not a git repository — cannot update."
hermes_cmd_not_found: "✗ Could not locate the `hermes` command. Hermes is running, but the update command could not find the executable on PATH or via the current Python interpreter. Try running `hermes update` manually in your terminal."
start_failed: "✗ Failed to start update: {error}"
starting: "⚕ Starting Hermes update… I'll stream progress here."
usage:
rate_limits: "⏱️ **Rate Limits:** {state}"
header_session: "📊 **Session Token Usage**"
label_model: "Model: `{model}`"
label_input_tokens: "Input tokens: {count}"
label_cache_read: "Cache read tokens: {count}"
label_cache_write: "Cache write tokens: {count}"
label_output_tokens: "Output tokens: {count}"
label_total: "Total: {count}"
label_api_calls: "API calls: {count}"
label_cost: "Cost: {prefix}${amount}"
label_cost_included: "Cost: included"
label_context: "Context: {used} / {total} ({pct}%)"
label_compressions: "Compressions: {count}"
header_session_info: "📊 **Session Info**"
label_messages: "Messages: {count}"
label_estimated_context: "Estimated context: ~{count} tokens"
detailed_after_first: "_(Detailed usage available after the first agent response)_"
no_data: "No usage data available for this session."
verbose:
not_enabled: "The `/verbose` command is not enabled for messaging platforms.\n\nEnable it in `config.yaml`:\n```yaml\ndisplay:\n tool_progress_command: true\n```"
mode_off: "⚙️ Tool progress: **OFF** — no tool activity shown."
mode_new: "⚙️ Tool progress: **NEW** — shown when tool changes (preview length: `display.tool_preview_length`, default 40)."
mode_all: "⚙️ Tool progress: **ALL** — every tool call shown (preview length: `display.tool_preview_length`, default 40)."
mode_verbose: "⚙️ Tool progress: **VERBOSE** — every tool call with full arguments."
saved_suffix: "_(saved for **{platform}** — takes effect on next message)_"
save_failed: "_(could not save to config: {error})_"
voice:
enabled_voice_only: "Voice mode enabled.\nI'll reply with voice when you send voice messages.\nUse /voice tts to get voice replies for all messages."
disabled_text: "Voice mode disabled. Text-only replies."
tts_enabled: "Auto-TTS enabled.\nAll replies will include a voice message."
status_mode: "Voice mode: {label}"
status_channel: "Voice channel: #{channel}"
status_participants: "Participants: {count}"
status_member: " - {name}{status}"
speaking: " (speaking)"
enabled_short: "Voice mode enabled."
disabled_short: "Voice mode disabled."
label_off: "Off (text only)"
label_voice_only: "On (voice reply to voice messages)"
label_all: "TTS (voice reply to all messages)"
yolo:
disabled: "⚠️ YOLO mode **OFF** for this session — dangerous commands will require approval."
enabled: "⚡ YOLO mode **ON** for this session — all commands auto-approved. Use with caution."
shared:
session_db_unavailable: "Session database not available."
session_db_unavailable_prefix: "Session database not available"
session_not_found: "Session not found in database."
warn_passthrough: "⚠️ {error}"